graph/ranking fixes
graph/ranking fixes


Former-commit-id: c08fb5bb63762d6d850ae16d8fc7ad947b845078

<?xml version="1.0" encoding="utf-8"?> <?xml version="1.0" encoding="utf-8"?>
<!-- Generator: Adobe Illustrator 15.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 0) --> <!-- Generator: Adobe Illustrator 15.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 0) -->
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"> <!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
<svg version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px" width="100px" <svg version="1.1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px" width="100px"
height="100px" viewBox="0 -25.635 100 100" enable-background="new 0 -25.635 100 100" xml:space="preserve"> height="100px" viewBox="0 -25.635 100 100" enable-background="new 0 -25.635 100 100" xml:space="preserve">
<g id="docs"> <g id="docs">
<path fill="#C2A385" d="M86.108-9.909l5.229,9.952c0,0-1.832,0.083-5.297,1.95c-2.312,1.249-6.468,6.246-6.468,6.246L71.827-2.909 <path fill="#C2A385" d="M86.108-9.909l5.229,9.952c0,0-1.832,0.083-5.297,1.95c-2.312,1.249-6.468,6.246-6.468,6.246L71.827-2.909
c0,0,4.201-3.996,6.513-5.242C81.805-10.022,86.108-9.909,86.108-9.909"/> c0,0,4.201-3.996,6.513-5.242C81.805-10.022,86.108-9.909,86.108-9.909"/>
<path fill="#C2A385" d="M65.604,20.731l-3.152-9.868c0,0-5.441,3.56-8.017,4.074c-1.008,0.202-1.93,0.335-2.749,0.425 <path fill="#C2A385" d="M65.604,20.731l-3.152-9.868c0,0-5.441,3.56-8.017,4.074c-1.008,0.202-1.93,0.335-2.749,0.425
L65.604,20.731z"/> L65.604,20.731z"/>
<path fill="#C2A385" d="M72.326,23.321c0.268-0.226,0.537-0.44,0.804-0.616c3.104-2.054,6.139-3.685,6.268-3.755l1.882-1.005 <path fill="#C2A385" d="M72.326,23.321c0.268-0.226,0.537-0.44,0.804-0.616c3.104-2.054,6.139-3.685,6.268-3.755l1.882-1.005
l1.369,1.634l2.864,3.417l3.198-4.334L76.68,9.783l-8.74,11.847L72.326,23.321z"/> l1.369,1.634l2.864,3.417l3.198-4.334L76.68,9.783l-8.74,11.847L72.326,23.321z"/>
<path fill="#C2A385" d="M39.918,10.823l4.825,1.86l3.33,0.212c0.04,0.001,0.269,0.015,0.652,0.015c0.91,0,2.798-0.072,5.196-0.551 <path fill="#C2A385" d="M39.918,10.823l4.825,1.86l3.33,0.212c0.04,0.001,0.269,0.015,0.652,0.015c0.91,0,2.798-0.072,5.196-0.551
c1.427-0.284,5.007-2.332,7.092-3.695l2.889-1.888l1.05,3.285l2.496,7.812l5.889-7.985l-4.625,0.163l1.348-6.225L55.133,0.593 c1.427-0.284,5.007-2.332,7.092-3.695l2.889-1.888l1.05,3.285l2.496,7.812l5.889-7.985l-4.625,0.163l1.348-6.225L55.133,0.593
l-2.095,9.667c-0.531-2.599-1.841-5.727-1.841-5.727L37.709,6.055c0,0,0.885,2.206,1.586,4.529L39.918,10.823z"/> l-2.095,9.667c-0.531-2.599-1.841-5.727-1.841-5.727L37.709,6.055c0,0,0.885,2.206,1.586,4.529L39.918,10.823z"/>
<path fill="#C2A385" d="M91.233,45.562c-1.102-0.691-2.323-1.142-3.415-1.433l-3.779,9.804c1.932,1.246,5.197,5.738,5.197,5.738 <path fill="#C2A385" d="M91.233,45.562c-1.102-0.691-2.323-1.142-3.415-1.433l-3.779,9.804c1.932,1.246,5.197,5.738,5.197,5.738
l7.336-9.206C96.572,50.466,93.162,46.771,91.233,45.562z"/> l7.336-9.206C96.572,50.466,93.162,46.771,91.233,45.562z"/>
<path fill="#C2A385" d="M93.192,32.166l-3.656,1.224c-0.019,0.007-1.779,0.613-4.117,2.069l2.817,4.868l0.626,1.08 <path fill="#C2A385" d="M93.192,32.166l-3.656,1.224c-0.019,0.007-1.779,0.613-4.117,2.069l2.817,4.868l0.626,1.08
c3.306-0.562,7.727-1.922,7.727-1.922l-2.332-15.261c0,0-2.934,1.277-5.852,2.221l2.318,2.765L93.192,32.166z"/> c3.306-0.562,7.727-1.922,7.727-1.922l-2.332-15.261c0,0-2.934,1.277-5.852,2.221l2.318,2.765L93.192,32.166z"/>
<path fill="#C2A385" d="M79.272,25.999l0.864,0.334l0.46,0.801l3.503,6.05c2.646-1.636,4.611-2.287,4.611-2.287l-8.075-9.632 <path fill="#C2A385" d="M79.272,25.999l0.864,0.334l0.46,0.801l3.503,6.05c2.646-1.636,4.611-2.287,4.611-2.287l-8.075-9.632
c0,0-2.584,1.391-5.376,3.188L79.272,25.999z"/> c0,0-2.584,1.391-5.376,3.188L79.272,25.999z"/>
</g> </g>
<g id="trunk"> <g id="trunk">
<circle fill="#C00000" cx="66.019" cy="52.945" r="7.877"/> <circle fill="#C00000" cx="66.019" cy="52.945" r="7.877"/>
<circle fill="#C00000" cx="22.693" cy="52.945" r="7.877"/> <circle fill="#C00000" cx="22.693" cy="52.945" r="7.877"/>
<path fill="#C00000" d="M22.693,42.441c1.915,0,3.705,0.522,5.251,1.421V28.001H12.191L3,37.192v14.439h9.281 <path fill="#C00000" d="M22.693,42.441c1.915,0,3.705,0.522,5.251,1.421V28.001H12.191L3,37.192v14.439h9.281
C12.931,46.459,17.347,42.441,22.693,42.441z"/> C12.931,46.459,17.347,42.441,22.693,42.441z"/>
<path fill="#C00000" d="M55.925,50.075l-9.583-3.695H30.88c1.186,1.476,1.978,3.28,2.225,5.252h22.502 <path fill="#C00000" d="M55.925,50.075l-9.583-3.695H30.88c1.186,1.476,1.978,3.28,2.225,5.252h22.502
C55.674,51.1,55.78,50.58,55.925,50.075z"/> C55.674,51.1,55.78,50.58,55.925,50.075z"/>
<path fill="#C00000" d="M79.312,28.328L39.961,13.149l-9.384,24.335l26.381,10.174c1.824-3.115,5.198-5.218,9.062-5.218 <path fill="#C00000" d="M79.312,28.328L39.961,13.149l-9.384,24.335l26.381,10.174c1.824-3.115,5.198-5.218,9.062-5.218
c5.791,0,10.503,4.712,10.503,10.502c0,0.744-0.081,1.471-0.229,2.173l4.713,1.817L86.95,41.52L79.312,28.328z"/> c5.791,0,10.503,4.712,10.503,10.502c0,0.744-0.081,1.471-0.229,2.173l4.713,1.817L86.95,41.52L79.312,28.328z"/>
</g> </g>
</svg> </svg>
   
<?php <?php
   
require_once '../include/common.inc.php'; require_once '../include/common.inc.php';
//function createFOIDocumentsDesignDoc() { //function createFOIDocumentsDesignDoc() {
   
$foidb = $server->get_db('disclosr-foidocuments'); $foidb = $server->get_db('disclosr-foidocuments');
$obj = new stdClass(); $obj = new stdClass();
$obj->_id = "_design/" . urlencode("app"); $obj->_id = "_design/" . urlencode("app");
$obj->language = "javascript"; $obj->language = "javascript";
$obj->views->all->map = "function(doc) { emit(doc._id, doc); };"; $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
$obj->views->byDate->map = "function(doc) { if (doc.title != "Disclosure Log Updated") { emit(doc.date, doc); } };"; $obj->views->byDate->map = "function(doc) { if (doc.title != \"Disclosure Log Updated\") { emit(doc.date, doc); } };";
$obj->views->byDateMonthYear->map = "function(doc) { emit(doc.date, doc); };"; $obj->views->byDateMonthYear->map = "function(doc) { emit(doc.date, doc); };";
$obj->views->byDateMonthYear->reduce = "_count"; $obj->views->byDateMonthYear->reduce = "_count";
$obj->views->byAgencyID->map = "function(doc) { emit(doc.agencyID, doc); };"; $obj->views->byAgencyID->map = "function(doc) { emit(doc.agencyID, doc); };";
$obj->views->byAgencyID->reduce = "_count"; $obj->views->byAgencyID->reduce = "_count";
$obj->views->fieldNames->map = ' $obj->views->fieldNames->map = 'function(doc) { for(var propName in doc) { emit(propName, doc._id); }}';
function(doc) { $obj->views->fieldNames->reduce = 'function (key, values, rereduce) { return values.length; }';
for(var propName in doc) {  
emit(propName, doc._id);  
}  
   
}';  
$obj->views->fieldNames->reduce = 'function (key, values, rereduce) {  
return values.length;  
}';  
// allow safe updates (even if slightly slower due to extra: rev-detection check). // allow safe updates (even if slightly slower due to extra: rev-detection check).
$foidb->save($obj, true); $foidb->save($obj, true);
   
   
//function createDocumentsDesignDoc() { //function createDocumentsDesignDoc() {
$docdb = $server->get_db('disclosr-documents'); $docdb = $server->get_db('disclosr-documents');
   
$obj = new stdClass(); $obj = new stdClass();
$obj->_id = "_design/" . urlencode("app"); $obj->_id = "_design/" . urlencode("app");
$obj->language = "javascript"; $obj->language = "javascript";
$obj->views->web_server->map = "function(doc) {\n emit(doc.web_server, 1);\n}"; $obj->views->web_server->map = "function(doc) {\n emit(doc.web_server, 1);\n}";
$obj->views->web_server->reduce = "_sum"; $obj->views->web_server->reduce = "_sum";
$obj->views->byAgency->map = "function(doc) {\n emit(doc.agencyID, 1);\n}"; $obj->views->byAgency->map = "function(doc) {\n emit(doc.agencyID, 1);\n}";
$obj->views->byAgency->reduce = "_sum"; $obj->views->byAgency->reduce = "_sum";
$obj->views->byURL->map = "function(doc) {\n emit(doc.url, doc);\n}"; $obj->views->byURL->map = "function(doc) {\n emit(doc.url, doc);\n}";
$obj->views->agency->map = "function(doc) {\n emit(doc.agencyID, doc);\n}"; $obj->views->agency->map = "function(doc) {\n emit(doc.agencyID, doc);\n}";
$obj->views->byWebServer->map = "function(doc) {\n emit(doc.web_server, doc);\n}"; $obj->views->byWebServer->map = "function(doc) {\n emit(doc.web_server, doc);\n}";
   
$obj->views->datasets->map = "function(doc) {\nif (doc.fieldName == \"data\") {\n emit(doc._id, doc);\n}\n}"; $obj->views->datasets->map = "function(doc) {\nif (doc.fieldName == \"data\") {\n emit(doc._id, doc);\n}\n}";
$obj->views->datasetGroups->map = "function(doc) {\nif (doc.fieldName == \"data\") {\n doc.metadata[\"data.gov.au Category\"] && doc.metadata[\"data.gov.au Category\"].forEach(function(tag) {\n emit(tag, doc.url); \n });\n}\n}"; $obj->views->datasetGroups->map = "function(doc) {\nif (doc.fieldName == \"data\") {\n doc.metadata[\"data.gov.au Category\"] && doc.metadata[\"data.gov.au Category\"].forEach(function(tag) {\n emit(tag, doc.url); \n });\n}\n}";
$obj->views->getValidationRequired->map = "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}"; $obj->views->getValidationRequired->map = "function(doc) {\nif (doc.mime_type == \"text/html\" \n&& typeof(doc.validation) == \"undefined\") {\n emit(doc._id, doc._attachments);\n}\n}";
$docdb->save($obj, true); $docdb->save($obj, true);
   
   
   
   
//function createAgencyDesignDoc() { //function createAgencyDesignDoc() {
$db = $server->get_db('disclosr-agencies'); $db = $server->get_db('disclosr-agencies');
$obj = new stdClass(); $obj = new stdClass();
$obj->_id = "_design/" . urlencode("app"); $obj->_id = "_design/" . urlencode("app");
$obj->language = "javascript"; $obj->language = "javascript";
$obj->views->all->map = "function(doc) { emit(doc._id, doc); };"; $obj->views->all->map = "function(doc) { emit(doc._id, doc); };";
$obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };"; $obj->views->byABN->map = "function(doc) { emit(doc.abn, doc); };";
$obj->views->byCanonicalName->map = "function(doc) { $obj->views->byCanonicalName->map = "function(doc) {
if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') { if (doc.parentOrg || doc.orgType == 'FMA-DepartmentOfState') {
emit(doc.name, doc); emit(doc.name, doc);
} }
};"; };";
$obj->views->byDeptStateName->map = "function(doc) { $obj->views->byDeptStateName->map = "function(doc) {
if (doc.orgType == 'FMA-DepartmentOfState') { if (doc.orgType == 'FMA-DepartmentOfState') {
emit(doc.name, doc._id); emit(doc.name, doc._id);
} }
};"; };";
$obj->views->parentOrgs->map = "function(doc) { $obj->views->parentOrgs->map = "function(doc) {
if (doc.parentOrg) { if (doc.parentOrg) {
emit(doc._id, doc.parentOrg); emit(doc._id, doc.parentOrg);
} }
};"; };";
$obj->views->byName->map = 'function(doc) { $obj->views->byName->map = 'function(doc) {
if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") { if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
emit(doc.name, doc._id); emit(doc.name, doc._id);
if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) { if (typeof(doc.shortName) != "undefined" && doc.shortName != doc.name) {
emit(doc.shortName, doc._id); emit(doc.shortName, doc._id);
} }
for (name in doc.otherNames) { for (name in doc.otherNames) {
if (doc.otherNames[name] != "" && doc.otherNames[name] != doc.name) { if (doc.otherNames[name] != "" && doc.otherNames[name] != doc.name) {
emit(doc.otherNames[name], doc._id); emit(doc.otherNames[name], doc._id);
} }
} }
for (name in doc.foiBodies) { for (name in doc.foiBodies) {
if (doc.foiBodies[name] != "" && doc.foiBodies[name] != doc.name) { if (doc.foiBodies[name] != "" && doc.foiBodies[name] != doc.name) {
emit(doc.foiBodies[name], doc._id); emit(doc.foiBodies[name], doc._id);
} }
} }
for (name in doc.positions) { for (name in doc.positions) {
if (doc.positions[name] != "" && doc.positions[name] != doc.name) { if (doc.positions[name] != "" && doc.positions[name] != doc.name) {
emit(doc.positions[name], doc._id); emit(doc.positions[name], doc._id);
} }
} }
} }
};'; };';
   
$obj->views->foiEmails->map = "function(doc) { $obj->views->foiEmails->map = "function(doc) {
emit(doc._id, doc.foiEmail); emit(doc._id, doc.foiEmail);
};"; };";
   
$obj->views->byLastModified->map = "function(doc) { emit(doc.metadata.lastModified, doc); }"; $obj->views->byLastModified->map = "function(doc) { emit(doc.metadata.lastModified, doc); }";
$obj->views->getActive->map = 'function(doc) { if (doc.status == "active") { emit(doc._id, doc); } };'; $obj->views->getActive->map = 'function(doc) { if (doc.status == "active") { emit(doc._id, doc); } };';
$obj->views->getSuspended->map = 'function(doc) { if (doc.status == "suspended") { emit(doc._id, doc); } };'; $obj->views->getSuspended->map = 'function(doc) { if (doc.status == "suspended") { emit(doc._id, doc); } };';
$obj->views->getScrapeRequired->map = "function(doc) { $obj->views->getScrapeRequired->map = "function(doc) {
   
var lastScrape = Date.parse(doc.metadata.lastScraped); var lastScrape = Date.parse(doc.metadata.lastScraped);
   
var today = new Date(); var today = new Date();
   
if (!lastScrape || lastScrape.getTime() + 1000 != today.getTime()) { if (!lastScrape || lastScrape.getTime() + 1000 != today.getTime()) {
emit(doc._id, doc); emit(doc._id, doc);
} }
   
};"; };";
$obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };"; $obj->views->showNamesABNs->map = "function(doc) { emit(doc._id, {name: doc.name, abn: doc.abn}); };";
$obj->views->getConflicts->map = "function(doc) { $obj->views->getConflicts->map = "function(doc) {
if (doc._conflicts) { if (doc._conflicts) {
emit(null, [doc._rev].concat(doc._conflicts)); emit(null, [doc._rev].concat(doc._conflicts));
} }
}"; }";
$obj->views->getStatistics->map = $obj->views->getStatistics->map =
"function(doc) { "function(doc) {
if (doc.statistics) { if (doc.statistics) {
for (var statisticSet in doc.statistics) { for (var statisticSet in doc.statistics) {
for (var statisticPeriod in doc.statistics[statisticSet]) { for (var statisticPeriod in doc.statistics[statisticSet]) {
emit([statisticSet,statisticPeriod], doc.statistics[statisticSet][statisticPeriod]['value']); emit([statisticSet,statisticPeriod], doc.statistics[statisticSet][statisticPeriod]['value']);
} }
} }
} }
}"; }";
$obj->views->getStatistics->reduce = '_sum'; $obj->views->getStatistics->reduce = '_sum';
// http://stackoverflow.com/questions/646628/javascript-startswith // http://stackoverflow.com/questions/646628/javascript-startswith
$obj->views->score->map = 'if(!String.prototype.startsWith){ $obj->views->score->map = 'if(!String.prototype.startsWith){
String.prototype.startsWith = function (str) { String.prototype.startsWith = function (str) {
return !this.indexOf(str); return !this.indexOf(str);
} }
} }
   
function(doc) { function(doc) {
count = 0; count = 0;
if (doc["status"] != "suspended") { if (doc["status"] != "suspended") {
for(var propName in doc) { for(var propName in doc) {
if(typeof(doc[propName]) != "undefined" && doc[propName] != "") { if(typeof(doc[propName]) != "undefined" && doc[propName] != "") {
count++; count++;
} }
} }
portfolio = doc.parentOrg; portfolio = doc.parentOrg;
if (doc.orgType == "FMA-DepartmentOfState") { if (doc.orgType == "FMA-DepartmentOfState") {
portfolio = doc._id; portfolio = doc._id;
} }
if (doc.orgType == "Court-Commonwealth" || doc.orgType == "FMA-DepartmentOfParliament") { if (doc.orgType == "Court-Commonwealth" || doc.orgType == "FMA-DepartmentOfParliament") {
portfolio = doc.orgType; portfolio = doc.orgType;
} }
emit(count+doc._id, {id:doc._id, name: doc.name, score:count, orgType: doc.orgType, portfolio:portfolio}); emit(count+doc._id, {id:doc._id, name: doc.name, score:count, orgType: doc.orgType, portfolio:portfolio});
} }
}'; }';
$obj->views->scoreHas->map = 'if(!String.prototype.startsWith){ $obj->views->scoreHas->map = 'if(!String.prototype.startsWith){
String.prototype.startsWith = function (str) { String.prototype.startsWith = function (str) {
return !this.indexOf(str); return !this.indexOf(str);
} }
} }
if(!String.prototype.endsWith){ if(!String.prototype.endsWith){
String.prototype.endsWith = function(suffix) { String.prototype.endsWith = function(suffix) {
    return this.indexOf(suffix, this.length - suffix.length) !== -1;     return this.indexOf(suffix, this.length - suffix.length) !== -1;
}; };
} }
function(doc) { function(doc) {
if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") { if (typeof(doc["status"]) == "undefined" || doc["status"] != "suspended") {
for(var propName in doc) { for(var propName in doc) {
if(typeof(doc[propName]) != "undefined" && (propName.startsWith("has") || propName.endsWith("URL"))) { if(typeof(doc[propName]) != "undefined" && (propName.startsWith("has") || propName.endsWith("URL"))) {
emit(propName, 1); emit(propName, 1);
} }
} }
emit("total", 1); emit("total", 1);
} }
}'; }';
$obj->views->scoreHas->reduce = '_sum'; $obj->views->scoreHas->reduce = '_sum';
$obj->views->fieldNames->map = ' $obj->views->fieldNames->map = '
function(doc) { function(doc) {
for(var propName in doc) { for(var propName in doc) {
emit(propName, doc._id); emit(propName, doc._id);
} }
}'; }';
$obj->views->fieldNames->reduce = '_count'; $obj->views->fieldNames->reduce = '_count';
// allow safe updates (even if slightly slower due to extra: rev-detection check). // allow safe updates (even if slightly slower due to extra: rev-detection check).
$db->save($obj, true); $db->save($obj, true);
?> ?>
   
# www.robotstxt.org/ # www.robotstxt.org/
# http://code.google.com/web/controlcrawlindex/ # http://code.google.com/web/controlcrawlindex/
   
User-agent: * User-agent: *
Disallow: /admin/ Disallow: /admin/
  Disallow: /viewDocument.php
Sitemap: http://disclosurelo.gs/sitemap.xml.php Sitemap: http://disclosurelo.gs/sitemap.xml.php
#http://packages.python.org/CouchDB/client.html #http://packages.python.org/CouchDB/client.html
import couchdb import couchdb
import urllib2 import urllib2
from BeautifulSoup import BeautifulSoup from BeautifulSoup import BeautifulSoup
import re import re
import hashlib import hashlib
from urlparse import urljoin from urlparse import urljoin
import time import time
import os import os
import sys import sys
import mimetypes import mimetypes
import urllib import urllib
import urlparse import urlparse
import socket import socket
   
#couch = couchdb.Server('http://192.168.1.148:5984/') #couch = couchdb.Server('http://192.168.1.148:5984/')
#couch = couchdb.Server('http://192.168.1.113:5984/') #couch = couchdb.Server('http://192.168.1.113:5984/')
couch = couchdb.Server('http://127.0.0.1:5984/') couch = couchdb.Server('http://127.0.0.1:5984/')
   
   
def mkhash(input): def mkhash(input):
return hashlib.md5(input).hexdigest().encode("utf-8") return hashlib.md5(input).hexdigest().encode("utf-8")
   
   
def canonurl(url): def canonurl(url):
r"""Return the canonical, ASCII-encoded form of a UTF-8 encoded URL, or '' r"""Return the canonical, ASCII-encoded form of a UTF-8 encoded URL, or ''
if the URL looks invalid. if the URL looks invalid.
>>> canonurl('\xe2\x9e\xa1.ws') # tinyarro.ws >>> canonurl('\xe2\x9e\xa1.ws') # tinyarro.ws
'http://xn--hgi.ws/' 'http://xn--hgi.ws/'
""" """
# strip spaces at the ends and ensure it's prefixed with 'scheme://' # strip spaces at the ends and ensure it's prefixed with 'scheme://'
url = url.strip() url = url.strip()
if not url: if not url:
return '' return ''
if not urlparse.urlsplit(url).scheme: if not urlparse.urlsplit(url).scheme:
url = 'http://' + url url = 'http://' + url
   
# turn it into Unicode # turn it into Unicode
#try: #try:
# url = unicode(url, 'utf-8') # url = unicode(url, 'utf-8')
#except UnicodeDecodeError: #except UnicodeDecodeError:
# return '' # bad UTF-8 chars in URL # return '' # bad UTF-8 chars in URL
   
# parse the URL into its components # parse the URL into its components
parsed = urlparse.urlsplit(url) parsed = urlparse.urlsplit(url)